After implemented this hook, we will model the memory dependency in the scheduling dependency graph more precise,
and will have more opportunity to reorder the load/stores, as they didn't have the dependency at some condition
Differential Revision: https://reviews.llvm.org/D63804
llvm-svn: 364886
return LoopCountReg;
}
+// Return true if get the base operand, byte offset of an instruction and the
+// memory width. Width is the size of memory that is being loaded/stored.
+bool PPCInstrInfo::getMemOperandWithOffsetWidth(
+ const MachineInstr &LdSt,
+ const MachineOperand *&BaseReg,
+ int64_t &Offset,
+ unsigned &Width,
+ const TargetRegisterInfo *TRI) const {
+ assert(LdSt.mayLoadOrStore() && "Expected a memory operation.");
+
+ // Handle only loads/stores with base register followed by immediate offset.
+ if (LdSt.getNumExplicitOperands() != 3)
+ return false;
+ if (!LdSt.getOperand(1).isImm() || !LdSt.getOperand(2).isReg())
+ return false;
+
+ if (!LdSt.hasOneMemOperand())
+ return false;
+
+ Width = (*LdSt.memoperands_begin())->getSize();
+ Offset = LdSt.getOperand(1).getImm();
+ BaseReg = &LdSt.getOperand(2);
+ return true;
+}
+
+bool PPCInstrInfo::areMemAccessesTriviallyDisjoint(
+ const MachineInstr &MIa, const MachineInstr &MIb,
+ AliasAnalysis * /*AA*/) const {
+ assert(MIa.mayLoadOrStore() && "MIa must be a load or store.");
+ assert(MIb.mayLoadOrStore() && "MIb must be a load or store.");
+
+ if (MIa.hasUnmodeledSideEffects() || MIb.hasUnmodeledSideEffects() ||
+ MIa.hasOrderedMemoryRef() || MIb.hasOrderedMemoryRef())
+ return false;
+
+ // Retrieve the base register, offset from the base register and width. Width
+ // is the size of memory that is being loaded/stored (e.g. 1, 2, 4). If
+ // base registers are identical, and the offset of a lower memory access +
+ // the width doesn't overlap the offset of a higher memory access,
+ // then the memory accesses are different.
+ const TargetRegisterInfo *TRI = &getRegisterInfo();
+ const MachineOperand *BaseOpA = nullptr, *BaseOpB = nullptr;
+ int64_t OffsetA = 0, OffsetB = 0;
+ unsigned int WidthA = 0, WidthB = 0;
+ if (getMemOperandWithOffsetWidth(MIa, BaseOpA, OffsetA, WidthA, TRI) &&
+ getMemOperandWithOffsetWidth(MIb, BaseOpB, OffsetB, WidthB, TRI)) {
+ if (BaseOpA->isIdenticalTo(*BaseOpB)) {
+ int LowOffset = std::min(OffsetA, OffsetB);
+ int HighOffset = std::max(OffsetA, OffsetB);
+ int LowWidth = (LowOffset == OffsetA) ? WidthA : WidthB;
+ if (LowOffset + LowWidth <= HighOffset)
+ return true;
+ }
+ }
+ return false;
+}
unsigned SrcReg2, int Mask, int Value,
const MachineRegisterInfo *MRI) const override;
+
+ /// Return true if get the base operand, byte offset of an instruction and
+ /// the memory width. Width is the size of memory that is being
+ /// loaded/stored (e.g. 1, 2, 4, 8).
+ bool getMemOperandWithOffsetWidth(const MachineInstr &LdSt,
+ const MachineOperand *&BaseOp,
+ int64_t &Offset, unsigned &Width,
+ const TargetRegisterInfo *TRI) const;
+
+ /// Return true if two MIs access different memory addresses and false
+ /// otherwise
+ bool
+ areMemAccessesTriviallyDisjoint(const MachineInstr &MIa,
+ const MachineInstr &MIb,
+ AliasAnalysis *AA = nullptr) const override;
+
/// GetInstSize - Return the number of bytes of code the specified
/// instruction may be. This returns the maximum number of bytes.
///
; CHECK-NEXT: stw 30, 416(1) # 4-byte Folded Spill
; CHECK-NEXT: lis 3, .LCPI0_0@ha
; CHECK-NEXT: stw 12, 408(1)
+; CHECK-NEXT: stfd 2, 376(1)
; CHECK-NEXT: stfd 27, 424(1) # 8-byte Folded Spill
+; CHECK-NEXT: stfd 1, 384(1)
; CHECK-NEXT: stfd 28, 432(1) # 8-byte Folded Spill
; CHECK-NEXT: stfd 29, 440(1) # 8-byte Folded Spill
; CHECK-NEXT: stfd 30, 448(1) # 8-byte Folded Spill
; CHECK-NEXT: stfd 31, 456(1) # 8-byte Folded Spill
-; CHECK-NEXT: stfd 2, 376(1)
-; CHECK-NEXT: lfs 27, .LCPI0_0@l(3)
-; CHECK-NEXT: stfd 1, 384(1)
; CHECK-NEXT: lwz 4, 380(1)
+; CHECK-NEXT: lfs 27, .LCPI0_0@l(3)
+; CHECK-NEXT: lwz 3, 384(1)
+; CHECK-NEXT: stw 4, 396(1)
; CHECK-NEXT: fcmpu 0, 2, 27
+; CHECK-NEXT: lwz 4, 376(1)
; CHECK-NEXT: fcmpu 1, 1, 27
; CHECK-NEXT: crand 20, 6, 0
-; CHECK-NEXT: stw 4, 396(1)
; CHECK-NEXT: cror 20, 4, 20
-; CHECK-NEXT: lwz 4, 376(1)
; CHECK-NEXT: stw 4, 392(1)
+; CHECK-NEXT: stw 3, 400(1)
; CHECK-NEXT: lwz 4, 388(1)
; CHECK-NEXT: stw 4, 404(1)
-; CHECK-NEXT: lwz 3, 384(1)
-; CHECK-NEXT: stw 3, 400(1)
; CHECK-NEXT: bc 4, 20, .LBB0_2
; CHECK-NEXT: # %bb.1: # %bb5
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: b .LBB0_16
; CHECK-NEXT: .LBB0_2: # %bb1
; CHECK-NEXT: lfd 0, 400(1)
+; CHECK-NEXT: lis 3, 15856
+; CHECK-NEXT: stw 3, 336(1)
; CHECK-NEXT: lfd 1, 392(1)
; CHECK-NEXT: li 29, 0
-; CHECK-NEXT: lis 3, 15856
; CHECK-NEXT: stfd 0, 304(1)
-; CHECK-NEXT: stfd 1, 296(1)
; CHECK-NEXT: stw 29, 340(1)
-; CHECK-NEXT: stw 3, 336(1)
; CHECK-NEXT: stw 29, 332(1)
; CHECK-NEXT: stw 29, 328(1)
; CHECK-NEXT: lwz 3, 308(1)
+; CHECK-NEXT: stfd 1, 296(1)
+; CHECK-NEXT: lfd 3, 336(1)
+; CHECK-NEXT: lfd 4, 328(1)
; CHECK-NEXT: stw 3, 324(1)
; CHECK-NEXT: lwz 3, 304(1)
; CHECK-NEXT: stw 3, 320(1)
; CHECK-NEXT: lwz 3, 300(1)
+; CHECK-NEXT: lfd 31, 320(1)
; CHECK-NEXT: stw 3, 316(1)
+; CHECK-NEXT: fmr 1, 31
; CHECK-NEXT: lwz 3, 296(1)
; CHECK-NEXT: stw 3, 312(1)
-; CHECK-NEXT: lfd 31, 320(1)
; CHECK-NEXT: lfd 30, 312(1)
-; CHECK-NEXT: lfd 3, 336(1)
-; CHECK-NEXT: lfd 4, 328(1)
-; CHECK-NEXT: fmr 1, 31
; CHECK-NEXT: fmr 2, 30
; CHECK-NEXT: bl __gcc_qmul@PLT
; CHECK-NEXT: lis 3, 16864
; CHECK-NEXT: stfd 1, 280(1)
-; CHECK-NEXT: fmr 29, 1
+; CHECK-NEXT: stw 3, 368(1)
; CHECK-NEXT: stfd 2, 288(1)
-; CHECK-NEXT: fmr 28, 2
; CHECK-NEXT: stw 29, 372(1)
-; CHECK-NEXT: stw 3, 368(1)
; CHECK-NEXT: stw 29, 364(1)
; CHECK-NEXT: stw 29, 360(1)
+; CHECK-NEXT: fmr 29, 1
; CHECK-NEXT: lwz 3, 284(1)
+; CHECK-NEXT: fmr 28, 2
+; CHECK-NEXT: lfd 3, 368(1)
+; CHECK-NEXT: lfd 4, 360(1)
; CHECK-NEXT: stw 3, 356(1)
; CHECK-NEXT: lwz 3, 280(1)
; CHECK-NEXT: stw 3, 352(1)
; CHECK-NEXT: lwz 3, 292(1)
+; CHECK-NEXT: lfd 1, 352(1)
; CHECK-NEXT: stw 3, 348(1)
; CHECK-NEXT: lwz 3, 288(1)
; CHECK-NEXT: stw 3, 344(1)
-; CHECK-NEXT: lfd 3, 368(1)
-; CHECK-NEXT: lfd 4, 360(1)
-; CHECK-NEXT: lfd 1, 352(1)
; CHECK-NEXT: lfd 2, 344(1)
; CHECK-NEXT: bl __gcc_qsub@PLT
; CHECK-NEXT: mffs 0
; CHECK-NEXT: lfs 1, .LCPI0_1@l(3)
; CHECK-NEXT: fctiwz 0, 0
; CHECK-NEXT: stfd 0, 152(1)
-; CHECK-NEXT: fcmpu 1, 29, 1
; CHECK-NEXT: lwz 3, 164(1)
+; CHECK-NEXT: fcmpu 1, 29, 1
; CHECK-NEXT: lwz 4, 156(1)
; CHECK-NEXT: crandc 20, 6, 0
; CHECK-NEXT: cror 20, 5, 20
; CHECK-NEXT: bl __floatditf@PLT
; CHECK-NEXT: lis 3, 17392
; CHECK-NEXT: stfd 1, 208(1)
-; CHECK-NEXT: fmr 29, 1
+; CHECK-NEXT: stw 3, 240(1)
; CHECK-NEXT: stfd 2, 200(1)
-; CHECK-NEXT: fmr 28, 2
; CHECK-NEXT: stw 29, 244(1)
-; CHECK-NEXT: stw 3, 240(1)
-; CHECK-NEXT: cmpwi 2, 30, 0
; CHECK-NEXT: stw 29, 236(1)
; CHECK-NEXT: stw 29, 232(1)
+; CHECK-NEXT: fmr 29, 1
; CHECK-NEXT: lwz 3, 212(1)
+; CHECK-NEXT: fmr 28, 2
+; CHECK-NEXT: lfd 3, 240(1)
+; CHECK-NEXT: lfd 4, 232(1)
+; CHECK-NEXT: cmpwi 2, 30, 0
; CHECK-NEXT: stw 3, 228(1)
; CHECK-NEXT: lwz 3, 208(1)
; CHECK-NEXT: stw 3, 224(1)
; CHECK-NEXT: lwz 3, 204(1)
+; CHECK-NEXT: lfd 1, 224(1)
; CHECK-NEXT: stw 3, 220(1)
; CHECK-NEXT: lwz 3, 200(1)
; CHECK-NEXT: stw 3, 216(1)
-; CHECK-NEXT: lfd 3, 240(1)
-; CHECK-NEXT: lfd 4, 232(1)
-; CHECK-NEXT: lfd 1, 224(1)
; CHECK-NEXT: lfd 2, 216(1)
; CHECK-NEXT: bl __gcc_qadd@PLT
; CHECK-NEXT: blt 2, .LBB0_7
; CHECK-NEXT: fmr 1, 29
; CHECK-NEXT: .LBB0_9: # %bb1
; CHECK-NEXT: stfd 1, 184(1)
-; CHECK-NEXT: fmr 1, 31
; CHECK-NEXT: stfd 2, 192(1)
-; CHECK-NEXT: fmr 2, 30
+; CHECK-NEXT: fmr 1, 31
; CHECK-NEXT: lwz 3, 188(1)
+; CHECK-NEXT: fmr 2, 30
; CHECK-NEXT: stw 3, 260(1)
; CHECK-NEXT: lwz 3, 184(1)
; CHECK-NEXT: stw 3, 256(1)
; CHECK-NEXT: lwz 3, 196(1)
+; CHECK-NEXT: lfd 3, 256(1)
; CHECK-NEXT: stw 3, 252(1)
; CHECK-NEXT: lwz 3, 192(1)
; CHECK-NEXT: stw 3, 248(1)
-; CHECK-NEXT: lfd 3, 256(1)
; CHECK-NEXT: lfd 4, 248(1)
; CHECK-NEXT: bl __gcc_qsub@PLT
; CHECK-NEXT: stfd 2, 176(1)
-; CHECK-NEXT: fcmpu 0, 2, 27
; CHECK-NEXT: stfd 1, 168(1)
-; CHECK-NEXT: fcmpu 1, 1, 27
+; CHECK-NEXT: fcmpu 0, 2, 27
; CHECK-NEXT: lwz 3, 180(1)
+; CHECK-NEXT: fcmpu 1, 1, 27
; CHECK-NEXT: crandc 20, 6, 0
; CHECK-NEXT: cror 21, 5, 7
-; CHECK-NEXT: cror 20, 21, 20
; CHECK-NEXT: stw 3, 268(1)
+; CHECK-NEXT: cror 20, 21, 20
; CHECK-NEXT: lwz 3, 176(1)
; CHECK-NEXT: stw 3, 264(1)
; CHECK-NEXT: lwz 3, 172(1)
+; CHECK-NEXT: lfd 30, 264(1)
; CHECK-NEXT: stw 3, 276(1)
; CHECK-NEXT: lwz 3, 168(1)
; CHECK-NEXT: stw 3, 272(1)
-; CHECK-NEXT: lfd 30, 264(1)
; CHECK-NEXT: lfd 31, 272(1)
; CHECK-NEXT: bc 12, 20, .LBB0_13
; CHECK-NEXT: # %bb.10: # %bb2
-; CHECK-NEXT: fneg 29, 30
; CHECK-NEXT: fneg 28, 31
-; CHECK-NEXT: li 29, 0
-; CHECK-NEXT: lis 3, 16864
; CHECK-NEXT: stfd 28, 48(1)
+; CHECK-NEXT: lis 3, 16864
+; CHECK-NEXT: stw 3, 80(1)
+; CHECK-NEXT: fneg 29, 30
+; CHECK-NEXT: lwz 3, 52(1)
; CHECK-NEXT: stfd 29, 40(1)
+; CHECK-NEXT: li 29, 0
; CHECK-NEXT: stw 29, 84(1)
-; CHECK-NEXT: stw 3, 80(1)
; CHECK-NEXT: stw 29, 76(1)
; CHECK-NEXT: stw 29, 72(1)
-; CHECK-NEXT: lwz 3, 52(1)
; CHECK-NEXT: stw 3, 68(1)
+; CHECK-NEXT: lfd 3, 80(1)
+; CHECK-NEXT: lfd 4, 72(1)
; CHECK-NEXT: lwz 3, 48(1)
; CHECK-NEXT: stw 3, 64(1)
; CHECK-NEXT: lwz 3, 44(1)
+; CHECK-NEXT: lfd 1, 64(1)
; CHECK-NEXT: stw 3, 60(1)
; CHECK-NEXT: lwz 3, 40(1)
; CHECK-NEXT: stw 3, 56(1)
-; CHECK-NEXT: lfd 3, 80(1)
-; CHECK-NEXT: lfd 4, 72(1)
-; CHECK-NEXT: lfd 1, 64(1)
; CHECK-NEXT: lfd 2, 56(1)
; CHECK-NEXT: bl __gcc_qsub@PLT
; CHECK-NEXT: mffs 0
; CHECK-NEXT: fcmpu 0, 30, 0
; CHECK-NEXT: fctiwz 2, 2
; CHECK-NEXT: stfd 2, 24(1)
-; CHECK-NEXT: fcmpu 1, 31, 1
; CHECK-NEXT: lwz 3, 36(1)
+; CHECK-NEXT: fcmpu 1, 31, 1
; CHECK-NEXT: lwz 4, 28(1)
; CHECK-NEXT: crandc 20, 6, 1
; CHECK-NEXT: cror 20, 4, 20
; CHECK-NEXT: subfe 3, 29, 30
; CHECK-NEXT: b .LBB0_16
; CHECK-NEXT: .LBB0_13: # %bb3
-; CHECK-NEXT: li 3, 0
-; CHECK-NEXT: lis 4, 16864
; CHECK-NEXT: stfd 31, 112(1)
-; CHECK-NEXT: stfd 30, 104(1)
+; CHECK-NEXT: li 3, 0
; CHECK-NEXT: stw 3, 148(1)
-; CHECK-NEXT: stw 4, 144(1)
; CHECK-NEXT: stw 3, 140(1)
; CHECK-NEXT: stw 3, 136(1)
+; CHECK-NEXT: stfd 30, 104(1)
+; CHECK-NEXT: lis 4, 16864
; CHECK-NEXT: lwz 3, 116(1)
+; CHECK-NEXT: stw 4, 144(1)
+; CHECK-NEXT: lfd 4, 136(1)
; CHECK-NEXT: stw 3, 132(1)
+; CHECK-NEXT: lfd 3, 144(1)
; CHECK-NEXT: lwz 3, 112(1)
; CHECK-NEXT: stw 3, 128(1)
; CHECK-NEXT: lwz 3, 108(1)
+; CHECK-NEXT: lfd 1, 128(1)
; CHECK-NEXT: stw 3, 124(1)
; CHECK-NEXT: lwz 3, 104(1)
; CHECK-NEXT: stw 3, 120(1)
-; CHECK-NEXT: lfd 3, 144(1)
-; CHECK-NEXT: lfd 4, 136(1)
-; CHECK-NEXT: lfd 1, 128(1)
; CHECK-NEXT: lfd 2, 120(1)
; CHECK-NEXT: bl __gcc_qsub@PLT
; CHECK-NEXT: mffs 0
; CHECK-NEXT: fcmpu 0, 30, 0
; CHECK-NEXT: fctiwz 2, 2
; CHECK-NEXT: stfd 2, 88(1)
-; CHECK-NEXT: fcmpu 1, 31, 1
; CHECK-NEXT: lwz 3, 100(1)
+; CHECK-NEXT: fcmpu 1, 31, 1
; CHECK-NEXT: lwz 4, 92(1)
; CHECK-NEXT: crandc 20, 6, 0
; CHECK-NEXT: cror 20, 5, 20
; CHECK-NEXT: stb r4, 9(r5)
; CHECK-NEXT: rldicl r4, r7, 32, 56
; CHECK-NEXT: rldicl r6, r7, 8, 56
+; CHECK-NEXT: stb r3, 12(r5)
; CHECK-NEXT: stb r4, 0(r5)
; CHECK-NEXT: rldicl r4, r7, 16, 56
; CHECK-NEXT: stb r6, 3(r5)
; CHECK-NEXT: rldicl r4, r7, 24, 56
; CHECK-NEXT: stb r6, 10(r5)
; CHECK-NEXT: stb r4, 11(r5)
-; CHECK-NEXT: stb r3, 12(r5)
; CHECK-NEXT: blr
;
; CHECK-BE-LABEL: test_13_consecutive_stores_of_bytes:
align 16 %a) {
; CHECK-LABEL: testStruct_03:
; CHECK: # %bb.0: # %entry
+; CHECK: lxv v2, 128(r1)
; CHECK-DAG: std r10, 88(r1)
; CHECK-DAG: std r9, 80(r1)
; CHECK-DAG: std r8, 72(r1)
; CHECK-DAG: std r5, 48(r1)
; CHECK-DAG: std r4, 40(r1)
; CHECK-DAG: std r3, 32(r1)
-; CHECK-NEXT: lxv v2, 128(r1)
; CHECK-NEXT: blr
; CHECK-BE-LABEL: testStruct_03:
; CHECK-BE: # %bb.0: # %entry
+; CHECK-BE: lxv v2, 144(r1)
; CHECK-BE-DAG: std r10, 104(r1)
; CHECK-BE-DAG: std r9, 96(r1)
; CHECK-BE-DAG: std r8, 88(r1)
; CHECK-BE-DAG: std r5, 64(r1)
; CHECK-BE-DAG: std r4, 56(r1)
; CHECK-BE-DAG: std r3, 48(r1)
-; CHECK-BE-NEXT: lxv v2, 144(r1)
; CHECK-BE-NEXT: blr
entry:
%a7 = getelementptr inbounds %struct.With9fp128params,
define fp128 @testNestedAggregate(%struct.MixedC* byval nocapture readonly align 16 %a) {
; CHECK-LABEL: testNestedAggregate:
; CHECK: # %bb.0: # %entry
-; CHECK-DAG: std r10, 88(r1)
-; CHECK-DAG: std r9, 80(r1)
; CHECK-DAG: std r8, 72(r1)
; CHECK-DAG: std r7, 64(r1)
+; CHECK: lxv v2, 64(r1)
+; CHECK-DAG: std r10, 88(r1)
+; CHECK-DAG: std r9, 80(r1)
; CHECK-DAG: std r6, 56(r1)
; CHECK-DAG: std r5, 48(r1)
; CHECK-DAG: std r4, 40(r1)
; CHECK-DAG: std r3, 32(r1)
-; CHECK-NEXT: lxv v2, 64(r1)
; CHECK-NEXT: blr
; CHECK-BE-LABEL: testNestedAggregate:
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-DAG: std r8, 88(r1)
; CHECK-BE-DAG: std r7, 80(r1)
+; CHECK-BE-NEXT: lxv v2, 80(r1)
; CHECK-BE-DAG: std r10, 104(r1)
; CHECK-BE-DAG: std r9, 96(r1)
; CHECK-BE-DAG: std r6, 72(r1)
; CHECK-BE-DAG: std r5, 64(r1)
; CHECK-BE-DAG: std r4, 56(r1)
; CHECK-BE-DAG: std r3, 48(r1)
-; CHECK-BE-NEXT: lxv v2, 80(r1)
; CHECK-BE-NEXT: blr
entry:
%c = getelementptr inbounds %struct.MixedC, %struct.MixedC* %a, i64 0, i32 1, i32 1
define <8 x i32> @test_large_vec_vaarg(i32 %n, ...) {
; BE-LABEL: test_large_vec_vaarg:
; BE: # %bb.0:
+; BE-NEXT: ld 3, -8(1)
; BE-NEXT: std 4, 56(1)
; BE-NEXT: std 5, 64(1)
; BE-NEXT: std 6, 72(1)
; BE-NEXT: std 8, 88(1)
; BE-NEXT: std 9, 96(1)
; BE-NEXT: std 10, 104(1)
-; BE-NEXT: ld 3, -8(1)
; BE-NEXT: addi 3, 3, 15
; BE-NEXT: rldicr 3, 3, 0, 59
; BE-NEXT: addi 4, 3, 16
;
; LE-LABEL: test_large_vec_vaarg:
; LE: # %bb.0:
+; LE-NEXT: ld 3, -8(1)
; LE-NEXT: std 4, 40(1)
; LE-NEXT: std 5, 48(1)
; LE-NEXT: std 6, 56(1)
; LE-NEXT: std 7, 64(1)
+; LE-NEXT: addi 3, 3, 15
+; LE-NEXT: rldicr 3, 3, 0, 59
; LE-NEXT: std 8, 72(1)
; LE-NEXT: std 9, 80(1)
; LE-NEXT: std 10, 88(1)
-; LE-NEXT: ld 3, -8(1)
-; LE-NEXT: addi 3, 3, 15
-; LE-NEXT: rldicr 3, 3, 0, 59
; LE-NEXT: addi 4, 3, 31
; LE-NEXT: addi 5, 3, 16
; LE-NEXT: rldicr 4, 4, 0, 59
; left for long double type (4 registers in soft float mode). Instead in r8 register this
; argument put on stack.
; CHECK-NOT: mr 8, 4
-; CHECK: stw 7, 20(1)
; CHECK: stw 6, 16(1)
; CHECK: stw 5, 12(1)
; CHECK: stw 4, 8(1)
+; CHECK: stw 7, 20(1)
declare i32 @printf(i8* nocapture readonly, ...)
--- /dev/null
+; REQUIRES: asserts
+; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -verify-misched -debug-only=machine-scheduler -o - 2>&1 > /dev/null | FileCheck %s
+
+define i64 @store_disjoint_memory(i64* nocapture %P, i64 %v) {
+entry:
+; CHECK: ********** MI Scheduling **********
+; CHECK-LABEL: store_disjoint_memory:%bb.0
+; CHECK:SU(2): STD renamable $x4, 24, renamable $x5 :: (store 8 into %ir.arrayidx)
+; CHECK-NOT: Successors:
+; CHECK-NOT: SU(3): Ord Latency=0 Memory
+; CHECK:SU(3): STD renamable $x4, 16, renamable $x5 :: (store 8 into %ir.arrayidx1)
+; CHECK: Predecessors:
+; CHECK-NOT: SU(2): Ord Latency=0 Memory
+ %arrayidx = getelementptr inbounds i64, i64* %P, i64 3
+ store i64 %v, i64* %arrayidx
+ %arrayidx1 = getelementptr inbounds i64, i64* %P, i64 2
+ store i64 %v, i64* %arrayidx1
+ ret i64 %v
+}
; P32-LABEL: test1:
; P32: # %bb.0:
; P32-NEXT: lbz r4, 0(r3)
-; P32-NEXT: addi r5, r4, 1
-; P32-NEXT: stb r5, 0(r3)
-; P32-NEXT: cmpwi r4, 8
; P32-NEXT: lwz r5, 4(r3)
+; P32-NEXT: lwz r6, 8(r3)
+; P32-NEXT: addi r7, r4, 1
+; P32-NEXT: stb r7, 0(r3)
+; P32-NEXT: addi r7, r5, 4
+; P32-NEXT: cmpwi r4, 8
; P32-NEXT: slwi r4, r4, 2
-; P32-NEXT: addi r6, r5, 4
-; P32-NEXT: bc 12, lt, .LBB0_1
-; P32-NEXT: b .LBB0_2
-; P32-NEXT: .LBB0_1:
-; P32-NEXT: addi r6, r5, 0
+; P32-NEXT: add r4, r6, r4
+; P32-NEXT: bc 12, lt, .LBB0_2
+; P32-NEXT: # %bb.1:
+; P32-NEXT: ori r6, r7, 0
+; P32-NEXT: b .LBB0_3
; P32-NEXT: .LBB0_2:
+; P32-NEXT: addi r6, r5, 0
+; P32-NEXT: .LBB0_3:
; P32-NEXT: stw r6, 4(r3)
-; P32-NEXT: lwz r3, 8(r3)
-; P32-NEXT: add r3, r3, r4
-; P32-NEXT: bc 12, lt, .LBB0_4
-; P32-NEXT: # %bb.3:
+; P32-NEXT: bc 12, lt, .LBB0_5
+; P32-NEXT: # %bb.4:
; P32-NEXT: ori r3, r5, 0
-; P32-NEXT: b .LBB0_4
-; P32-NEXT: .LBB0_4:
+; P32-NEXT: b .LBB0_6
+; P32-NEXT: .LBB0_5:
+; P32-NEXT: addi r3, r4, 0
+; P32-NEXT: .LBB0_6:
; P32-NEXT: lwz r3, 0(r3)
; P32-NEXT: blr
;
; NOP8VEC-NEXT: stxvd2x 1, 0, 4
; NOP8VEC-NEXT: ld 3, -24(1)
; NOP8VEC-NEXT: ld 4, -40(1)
+; NOP8VEC-NEXT: ld 6, -48(1)
; NOP8VEC-NEXT: cmpd 4, 3
; NOP8VEC-NEXT: li 3, 0
; NOP8VEC-NEXT: li 4, -1
; NOP8VEC-NEXT: isel 5, 4, 3, 1
; NOP8VEC-NEXT: std 5, -8(1)
; NOP8VEC-NEXT: ld 5, -32(1)
-; NOP8VEC-NEXT: ld 6, -48(1)
; NOP8VEC-NEXT: cmpd 6, 5
; NOP8VEC-NEXT: isel 3, 4, 3, 1
; NOP8VEC-NEXT: std 3, -16(1)
; NOP8VEC-NEXT: stxvd2x 1, 0, 4
; NOP8VEC-NEXT: ld 3, -24(1)
; NOP8VEC-NEXT: ld 4, -40(1)
+; NOP8VEC-NEXT: ld 6, -48(1)
; NOP8VEC-NEXT: cmpd 4, 3
; NOP8VEC-NEXT: li 3, 0
; NOP8VEC-NEXT: li 4, -1
; NOP8VEC-NEXT: isel 5, 4, 3, 0
; NOP8VEC-NEXT: std 5, -8(1)
; NOP8VEC-NEXT: ld 5, -32(1)
-; NOP8VEC-NEXT: ld 6, -48(1)
; NOP8VEC-NEXT: cmpd 6, 5
; NOP8VEC-NEXT: isel 3, 4, 3, 0
; NOP8VEC-NEXT: std 3, -16(1)
; CHECK-NEXT: ld r3, -24(r1)
; CHECK-NEXT: ld r4, -40(r1)
; CHECK-NEXT: add r3, r4, r3
+; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: ld r3, -32(r1)
-; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: add r3, r4, r3
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: ld r3, -24(r1)
; CHECK-REG-NEXT: ld r4, -40(r1)
; CHECK-REG-NEXT: add r3, r4, r3
+; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: ld r3, -32(r1)
-; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: add r3, r4, r3
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-NEXT: lwz r3, -20(r1)
; CHECK-NEXT: ld r4, -40(r1)
; CHECK-NEXT: sld r3, r4, r3
+; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: lwz r3, -28(r1)
-; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: sld r3, r4, r3
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lwz r3, -20(r1)
; CHECK-REG-NEXT: ld r4, -40(r1)
; CHECK-REG-NEXT: sld r3, r4, r3
+; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: lwz r3, -28(r1)
-; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: sld r3, r4, r3
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-NEXT: lwz r3, -20(r1)
; CHECK-NEXT: ld r4, -40(r1)
; CHECK-NEXT: srd r3, r4, r3
+; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: lwz r3, -28(r1)
-; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: srd r3, r4, r3
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lwz r3, -20(r1)
; CHECK-REG-NEXT: ld r4, -40(r1)
; CHECK-REG-NEXT: srd r3, r4, r3
+; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: lwz r3, -28(r1)
-; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: srd r3, r4, r3
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-NEXT: lwz r3, -20(r1)
; CHECK-NEXT: ld r4, -40(r1)
; CHECK-NEXT: srad r3, r4, r3
+; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: lwz r3, -28(r1)
-; CHECK-NEXT: ld r4, -48(r1)
; CHECK-NEXT: srad r3, r4, r3
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
; CHECK-REG-NEXT: lwz r3, -20(r1)
; CHECK-REG-NEXT: ld r4, -40(r1)
; CHECK-REG-NEXT: srad r3, r4, r3
+; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: lwz r3, -28(r1)
-; CHECK-REG-NEXT: ld r4, -48(r1)
; CHECK-REG-NEXT: srad r3, r4, r3
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
; CHECK-NEXT: stxvd2x v2, 0, r4
; CHECK-NEXT: ld r3, -24(r1)
; CHECK-NEXT: ld r4, -40(r1)
+; CHECK-NEXT: ld r6, -48(r1)
; CHECK-NEXT: cmpld r4, r3
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: li r4, -1
; CHECK-NEXT: isel r5, r4, r3, lt
; CHECK-NEXT: std r5, -8(r1)
; CHECK-NEXT: ld r5, -32(r1)
-; CHECK-NEXT: ld r6, -48(r1)
; CHECK-NEXT: cmpld r6, r5
; CHECK-NEXT: isel r3, r4, r3, lt
; CHECK-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: stxvd2x v2, 0, r4
; CHECK-REG-NEXT: ld r3, -24(r1)
; CHECK-REG-NEXT: ld r4, -40(r1)
+; CHECK-REG-NEXT: ld r6, -48(r1)
; CHECK-REG-NEXT: cmpld r4, r3
; CHECK-REG-NEXT: li r3, 0
; CHECK-REG-NEXT: li r4, -1
; CHECK-REG-NEXT: isel r5, r4, r3, lt
; CHECK-REG-NEXT: std r5, -8(r1)
; CHECK-REG-NEXT: ld r5, -32(r1)
-; CHECK-REG-NEXT: ld r6, -48(r1)
; CHECK-REG-NEXT: cmpld r6, r5
; CHECK-REG-NEXT: isel r3, r4, r3, lt
; CHECK-REG-NEXT: std r3, -16(r1)